Bacteria are ubiquitous and live in complex microbial communities, which can react rapidly to changing environmental conditions. Their physiological variety enables communities to respond in specific ways to environmental drivers, potentially resulting in distinct microbial fingerprints for a given environmental state. Our goal was to assess the opportunities and limitations of machine learning to detect fingerprints indicating the presence of the munition compound 2,4,6-trinitrotoluene (TNT) in southwestern Baltic Sea sediments. Over 40 environmental variables including grain size distribution, elemental composition and concentration of munition compounds (mostly at pmol g-1 levels) from 150 sediments collected at the near-to-shore munition dumpsite Kolberger Heide by the German city of Kiel were combined with 16S rRNA gene amplicon sequencing libraries. Prediction was achieved using Random Forests; the robustness of predictions was validated using Artificial Neural Networks. To facilitate machine learning with microbiome data we developed the R package phyloseq2ML. Using the most classification-relevant 25 bacterial genera exclusively, potentially representing a TNT-indicative fingerprint, TNT was predicted correctly with up to 81.5 % balanced accuracy. False positive classifications indicated that this approach has also the potential to identify samples where the original TNT contamination was no longer detectable. The sensitivity of this approach can be deduced from the fact that TNT presence was neither identified among the main drivers of the microbial community composition, nor did it correlate with sediment metal content, demonstrated by decreased prediction rates using environmental variables. Our results suggest that microbial communities can predict even minor influencing factors in complex environments, demonstrating the potential of this approach for the discovery of contamination events over an integrated period of time and for environmental monitoring in general.